CN113220678A - Ship berthing event identification method and system - Google Patents
Ship berthing event identification method and system Download PDFInfo
- Publication number
- CN113220678A CN113220678A CN202110442571.0A CN202110442571A CN113220678A CN 113220678 A CN113220678 A CN 113220678A CN 202110442571 A CN202110442571 A CN 202110442571A CN 113220678 A CN113220678 A CN 113220678A
- Authority
- CN
- China
- Prior art keywords
- ship
- grid
- background
- target
- track data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
- G06F16/2264—Multidimensional index structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Abstract
The invention provides a ship-approaching event identification method and a system, wherein the ship-approaching event identification method comprises the following steps: determining a target grid background; translating the target grid background along the diagonal line of the position grid to a first direction and a second direction respectively by a second target length, and determining a first reference grid background and a second reference grid background; acquiring ship track data; respectively mapping ship track data to a target background grid, a first reference grid background and a second reference grid background based on position information corresponding to the ship track data; and determining the distance between every two track points in each position grid of the target background grid, the first reference grid background and the second reference grid background, confirming that the distance between the two track points is smaller than a target distance threshold value, and outputting a ship approach event record. The ship berthing event identification method and the ship berthing event identification system can improve and reduce the calculation amount, accelerate the calculation speed and improve the accuracy and the efficiency.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a ship berthing event identification method and system.
Background
The ship-berthing event can reflect economic activities such as ship refueling, gas station monitoring, refute district and research and judgment trade trend, and can monitor the resources of stealing mining and transportation, so that the detection of the ship-berthing event becomes a technical problem concerned in the industry in the field of navigation.
At present, the detection of ship-approaching events usually adopts a scheme of monitoring partial ships in partial areas, and the calculated amount can be reduced by limiting the area range, but when a customer needs to monitor more areas, the requirement is difficult to meet; in addition, if snapshot information is established on global ships, the positions of all the ships at a certain time point can be observed, and the distance between every two ships can be calculated to identify ship-approaching events, but the calculation amount is large, the calculation speed is low, and the efficiency is low.
Disclosure of Invention
The invention provides a ship berthing event identification method and system, which are used for overcoming the defects of large calculation amount, low calculation speed and low efficiency in the prior art, and realizing the purposes of improving and reducing the calculation amount, accelerating the calculation speed and improving the accuracy and the efficiency.
The invention provides a ship-approaching event identification method, which comprises the following steps: determining a target grid background, wherein the target grid background is formed by a plurality of position grids with side length being a first target length constructed on a target map; translating the target grid background along the diagonal of the position grid by a second target length in a first direction and a second direction respectively, and determining a first reference grid background and a second reference grid background, wherein the second direction is opposite to the first direction; acquiring ship track data, wherein the ship track data comprises position information of each track point; respectively mapping the ship track data to the target background grid, the first reference grid background and the second reference grid background based on the position information corresponding to the ship track data; and determining the distance between every two track points in each position grid of the target background grid, the first reference grid background and the second reference grid background, confirming that the distance between the two track points is smaller than a target distance threshold value, and outputting a ship-approaching event record.
According to the ship-approaching event identification method provided by the invention, the ship-approaching event identification method further comprises the following steps: determining the position of a center point of the ship based on the ship track data; determining the distance between the central points of the two ships based on the distance between the two track points and the position of the central point of the ship; and updating the ship-approaching event record based on the distance between the central points of the two ships and the target distance threshold value to obtain an updated ship-approaching event record.
According to the ship-approaching event identification method provided by the invention, the ship-approaching event identification method further comprises the following steps: determining bow direction information of the ship based on the ship track data; and updating the ship-approaching event record based on the ship bow direction information of the ship to obtain an updated ship-approaching event record.
According to the ship approach event identification method provided by the invention, the step of acquiring ship track data comprises the following steps: obtaining the ship track data at intervals of a target time period threshold value; and if the ship track data is not acquired, taking historical track data as the ship track data.
According to the ship approach event identification method provided by the invention, the ship track data comprises the following steps: the MMSI of the vessel, the longitude of the vessel, and the latitude of the vessel; the mapping the ship track data to the target background grid, the first reference grid background and the second reference grid background respectively based on the position information corresponding to the ship track data includes: establishing index information of the ship track data and the target background grid, the first reference grid background and the second reference grid background based on the longitude of the ship and the latitude of the ship; adding the MMSI of the vessel, the longitude of the vessel, and the latitude of the vessel to the index information.
According to the ship berthing event identification method provided by the invention, the index information is established by the ship track data, the target background grid, the first reference grid background and the second reference grid background based on the longitude of the ship and the latitude of the ship, and the method comprises the following steps: establishing a first dimension index based on the longitude of the ship; establishing a second-dimension index based on the latitude of the ship; determining the index information based on the first dimension index and the second dimension index.
The present invention also provides a ship-on event recognition system, including: the system comprises a first determination module, a second determination module and a third determination module, wherein the first determination module is used for determining a target grid background, and the target grid background is formed by a plurality of position grids with the side length being a first target length and constructed on a target map; a second determining module, configured to translate the target grid background by a second target length along a diagonal of the position grid to a first direction and a second direction, respectively, and determine a first reference grid background and a second reference grid background, where the second direction is opposite to the first direction; the acquisition module is used for acquiring ship track data, and the ship track data comprises position information of each track point; the mapping module is used for mapping the ship track data to the target background grid, the first reference grid background and the second reference grid background respectively based on the position information corresponding to the ship track data; and the output module is used for determining the distance between every two track points in each position grid of the target background grid, the first reference grid background and the second reference grid background, confirming that the distance between the two track points is smaller than a target distance threshold value, and outputting a ship-approaching event record.
The invention further provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the ship berthing event identification method.
The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method of identifying a berthing event as claimed in any of the above.
According to the ship-approaching event identification method and system provided by the invention, the distance between the track points of the ship is calculated through the position grids of the three sets of grid backgrounds, so that the ship-approaching event is determined, the calculation amount can be increased and reduced, the calculation speed is increased, and the accuracy and the efficiency are improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for identifying a berthing event according to the present invention;
FIG. 2 is a schematic diagram of a method for identifying a berthing event according to the present invention;
FIG. 3 is a schematic structural diagram of a berthing event identification system provided by the present invention;
fig. 4 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The berthing event identification method of the present invention is described below with reference to fig. 1 to 4.
As shown in fig. 1, the present invention provides a ship-docking event recognition method including the following steps 110 to 150.
And step 110, determining a target grid background, wherein the target grid background is formed by a plurality of position grids with the side length being the length of the first target, which are constructed on a target map.
It is understood that the target map may be a global map, the target grid background may be a plurality of position grids divided by latitude and longitude on the global map, each position grid is a square with a side length of a first target length, and constructing the target grid background here is to divide the target map into the plurality of position grids, that is, to divide the target map into a plurality of identical units.
The first target side length may be one-twentieth of a degree longitude (latitude) and about 5.55km near the equator, and the global map may be partitioned into the plurality of location grids according to the first target side length.
And step 120, translating the target grid background by a second target length along the diagonal line of the position grid to a first direction and a second direction respectively, and determining a first reference grid background and a second reference grid background, wherein the second direction is opposite to the first direction.
It is understood that, as shown in fig. 2, the target mesh background constructed in step 110 is translated integrally twice along the diagonal of one position mesh, once translated to the first direction to obtain the first reference mesh background, and once translated to the second direction to obtain the second reference mesh background.
The first direction and the second direction are along the same diagonal of the position grid, the first direction can be the upper left, and the corresponding second direction is the lower right; the second direction may also be right-up, and the corresponding second direction is left-down.
The second target length may be half the first target length and the second target length may be one-quarter longitude (latitude), approximately 2.78 km.
The construction of the position grid is used as a core, the main innovation point of the embodiment is embodied, the position grid with fixed longitude and latitude step lengths is constructed on a map, the longitude and latitude step lengths come from engineering experience, so that a certain number of ships can be accommodated in a single position grid, and meanwhile, unnecessary calculation is reduced to the maximum extent. The method comprises the steps that when a target grid background is built, the longitude coordinates and the latitude coordinates of grids are translated, another first reference grid background and another second reference grid background are built, the translation directions are respectively from top left to bottom right (or from top right to bottom left), and therefore a ship located at the position grid boundary in the target grid background moves to the non-boundary positions of the first reference grid background and the second reference grid background through the offset between the grids, and potential ship-to-ship events which are possibly missed by a single set of grid backgrounds are avoided.
Three sets of grid backgrounds are constructed here, and can be used as scales for positioning ships.
And step 130, acquiring ship track data, wherein the ship track data comprises position information of each track point.
It can be understood that scanning can be regularly carried out here to obtain ship track data, and ship track data comprises a plurality of track points of boats and ships, and ship track data includes the positional information of every track point, and positional information can be represented by the longitude and latitude.
At the moment, the latest position of the ship is actually obtained at regular time, and three sets of grid background updating processes are driven according to the position of the ship. Compared with the updating frequency of the ship position, the updating frequency of the ship-approaching event is lower, the grid background is generally updated once in three minutes in real-time service to finish the updating of the ship event, and the grid background is generally updated once in ten minutes in the generation process of historical data to speed up the completion of the analysis of all historical ship positions.
And 140, respectively mapping the ship track data to a target background grid, a first reference grid background and a second reference grid background based on the position information corresponding to the ship track data.
It can be understood that, here, the ship track data can be mapped to the corresponding position grids according to the position information corresponding to each track point in the ship track data, that is, a classification operation is performed, the position information of the ship track data originally measured according to the global longitude and latitude coordinate system is converted into each position grid, and a connection can be established with the corresponding position grids.
The ship track data are mapped into the three sets of background grids respectively, so that the condition that a single background grid lacks some ship-berthing events can be avoided, and the mapping relation of the three sets of ship track data can be formed through the three sets of background grids.
And 150, determining the distance between every two track points in each position grid of the target background grid, the first reference grid background and the second reference grid background, confirming that the distance between the two track points is smaller than a target distance threshold value, and outputting a ship approach event record.
It can be understood that, focusing on each small cell, that is, each position grid, in the target background grid, the first reference grid background and the second reference grid background, counting all track points in each position grid, calculating a distance between every two track points, and if the distance between two track points is smaller than a target distance threshold, determining that a ship-to-ship event occurs in two ships corresponding to the two track points.
The target distance threshold may be 0.008 latitude and longitude (approximately 889 meters near the equator).
The distance calculation and comparison are put in each position grid, compared with the direct two-two distance calculation of all track points, the calculation amount can be greatly reduced, namely the track points are firstly classified into each small unit, the track points in the small units are certainly the track points with the closer distance, thus, the mapping algorithm with the small occupied calculation amount is utilized to carry out preliminary screening, the more complex distance calculation is carried out in each small unit, the calculation amount can be greatly reduced, the calculation speed is improved, and the efficiency is improved.
Meanwhile, considering that a set of grid backgrounds is used for calculation, two track points which are relatively close to each other may not fall on the same position grid, and thus identification of the ship-approaching event may be omitted, in this embodiment, a first reference grid background and a second reference grid background which are formed by translation of a target grid background are used as supplements, and three sets of grid backgrounds are used as a reference system together to complete identification of the ship-approaching event, so that accuracy of identification of the ship-approaching event can be improved.
Of course, mapping is performed by using three sets of grid backgrounds, repeated ship-to-ship event records may occur, duplication can be removed according to ship track data corresponding to the ship-to-ship event records at the moment, namely, the same ship-to-ship event is only recorded once, and thus repeated storage can be avoided.
According to the ship-approaching event identification method provided by the invention, the distance between the track points of the ship is calculated through the position grids of the three sets of grid backgrounds, so that the ship-approaching event is determined, the calculation amount can be increased and reduced, the calculation speed is increased, and the accuracy and the efficiency are improved.
In some embodiments, the berthing event identification method further comprises: based on the ship trajectory data, the position of the center point of the ship is determined. Determining the distance between the central points of the two ships based on the distance between the two track points and the position of the central point of the ship; and updating the ship-approaching event record based on the distance between the central points of the two ships and the target distance threshold value to obtain the updated ship-approaching event record.
It can be understood that, the distance between two track points is used to judge that there is certain error in the ship approach event, certain disparity still exists in the distance between two track points and the true distance between two boats and ships, the physical parameters of boats and ships can be discerned from boats and ships orbit data here, such as the length of boats and ships, the width, the port side apart from and the tail side apart from, the central point position of boats and ships is calculated through the physical parameters of boats and ships, the distance between two track points and the central point position of boats and ships are combined again, the distance between two track points can be converted into the distance between the central points of two boats and ships, the distance calculation can adopt the sphere distance computational formula.
And comparing the distance between the central points of the two ships with a target distance threshold, keeping the ship-approaching event record when the distance between the central points of the two ships is smaller than the target distance threshold, and deleting the ship-approaching event record when the distance between the central points of the two ships is larger than or equal to the target distance threshold.
That is, the ship-to-ship event records are further screened here, so that more accurate ship-to-ship event records can be obtained.
In some embodiments, the berthing event identification method further comprises: determining bow direction information of the ship based on the ship track data; and updating the ship-approaching event record based on the ship bow direction information to obtain the updated ship-approaching event record.
It can be understood that when the bow directions of the two ships are not nearly parallel, the ship-to-ship event cannot be considered, and here, the bow direction information of the ship is obtained according to the ship track data, and according to the bow direction information of the ship, the ship-to-ship event record obtained in the above embodiment can be further corrected and updated to obtain the ship-to-ship event update record.
In some embodiments, acquiring vessel trajectory data comprises: interval target time interval threshold values, and acquiring ship track data; and if the ship track data is not acquired, taking the historical track data as the ship track data.
It can be understood that if there is new ship position information in a fixed period, the new ship position information is used to update the old ship position information, otherwise, the ship position recorded before is still used to participate in the ship landing point calculation. The ship landing point calculation establishes the mapping relation between the ships and the grids, after the mapping relation of all the ships is established, the mapping relation is equivalent to that a snapshot is taken of the global ships, then the snapshots are analyzed point by point, namely, each position grid in the three sets of grid backgrounds is scanned one by one, the distance relation between all the ships in the position grids is calculated, when the distance meets a preset value, a potential ship-leaning event is judged, and after the three sets of grid backgrounds are scanned, all the potential ship-leaning events in the period are generated.
In some embodiments, all latitudes and longitudes in the calculation process are expressed by integers of one-ten-thousandth latitude or longitude, for example, 40500000 latitude represents 40 degrees and 30 minutes north latitude or 40.5 degrees north latitude; -41500000 latitude represents 41 degrees 30 minutes south latitude or 41.5 degrees south latitude; 120500000 longitude, 120 degrees 30 minutes east longitude or 120.5 degrees east longitude; longitude-121500000 represents 121 degrees 30 minutes for west longitude or 121.5 degrees for west longitude.
The longitude and latitude in this representation can be used to conveniently establish a mapping relationship between grid backgrounds, such as longitude and latitude, which are recorded as lon and lat, for a specific location. The method is characterized in that three sets of grid backgrounds are constructed based on a sliding window idea, the construction process is that a two-dimensional array is constructed firstly, the map represented by the array ranges from 80 degrees of south latitude to 80 degrees of north latitude, and from 180 degrees of west longitude to 180 degrees of east longitude, the first dimension of the corresponding two-dimensional array comprises 3200 elements, the second dimension of the corresponding two-dimensional array comprises 7200 elements, the two-dimensional array in the system is totally 9, and the two-dimensional array can be divided into 3 types according to functional differences.
The first two-dimensional Array is a grid background based on a sliding window idea, and 3 sets of two-dimensional arrays are provided, each set records ship identification, longitude and latitude in a grid and detailed information indexes of associated containers, the detailed information indexes are used for realizing high-speed data acquisition capacity, a specific Array type can be recorded as Array [ (Int ) ] ] ], the 3 sets of grid backgrounds can be respectively recorded as grid _ original, grid _ leftup and grid _ rightdown, the first one is a grid background without sliding, and the last two sets of grid backgrounds respectively slide with the side length of one half grid at the upper left and the lower right.
The second type of two-dimensional Array is an accompanying Array of the first type of two-dimensional Array, and records the number of the third-dimensional elements of each position grid in the first type of two-dimensional Array respectively for assisting in computation, the specific data type may be denoted as Array [ Int ] ], the 3 sets of grid backgrounds are denoted as grid _ original _ num, grid _ left _ num, and grid _ right _ num respectively, and the specific intra-class division is the same as the first class.
The third type of two-dimensional Array records the maximum element number of each grid background in order to realize memory space with difference in distribution to the first type of two-dimensional Array, the maximum element number is derived from the grid heat, the purpose is to accurately distribute memory resources to the first type of two-dimensional Array, the specific data type can be recorded as Array [ Int ] ], and the three sets of grid backgrounds are respectively recorded as grid _ original _ num _ limit, grid _ left _ num _ limit, and grid _ right _ num _ limit.
During engineering implementation, the third type of two-dimensional array is created first, and after the second type of two-dimensional array is created, different quantities of third-dimensional elements can be distributed to each position grid in the process of creating the first type of two-dimensional array, so that a large amount of memory resources can be saved. It must be emphasized that these three types of two-dimensional arrays employ a uniform partitioning method, i.e., 3200 by 7200 two-dimensional arrays.
In some embodiments, the vessel trajectory data comprises: the MMSI of the vessel, the longitude of the vessel, and the latitude of the vessel.
The MMSI of a ship refers to a marine Mobile Service identity code (Maritime Mobile Service identity) transmitted by a ship radio communication system over its radio channel, which uniquely identifies a list of nine-digit codes for various stations and group call stations.
Based on the position information corresponding to the ship track data, the ship track data are respectively mapped to a target background grid, a first reference grid background and a second reference grid background, and the method comprises the following steps: based on the longitude of the ship and the latitude of the ship, establishing index information between the ship track data and a target background grid, a first reference grid background and a second reference grid background; the MMSI of the vessel, the longitude of the vessel, and the latitude of the vessel are added to the index information.
It is understood that, taking a fixed clock period of 10 minutes as an example, when the timer is triggered, i.e. the ship track data within 10 minutes is obtained from the HBase in a time-slot manner, the HBase is a distributed and column-oriented open source database. When the ship track appears in the 10-minute period, the position information of the ship is updated, validity check is carried out before updating so as to avoid adopting position points such as flying spots, out of boundaries or reverse time sequence, and if the position information of the ship does not appear in the 10-minute period, the position information of the ship recorded before is used.
In some embodiments, indexing the vessel trajectory data with the target background grid, the first reference grid background, and the second reference grid background based on the longitude of the vessel and the latitude of the vessel comprises: establishing a first-dimension index based on the longitude of the ship; establishing a second-dimension index based on the latitude of the ship; index information is determined based on the first-dimension index and the second-dimension index.
It can be understood that after the update of the ship position is completed, the mapping relationship between the position information of the ship track data and the three sets of grid backgrounds starts to be established, specifically, when the mapping relationship is established between the target grid background and grid _ original, the index of the first dimension is lat/50000+1600, which is recorded as x _ original, and the index of the second dimension is lon/50000+3600, which is recorded as y _ original.
Thus, the ship information, specifically, the mmsi, longitude, latitude, and detailed information index is added to the grid _ original [ x _ original ] [ y _ original ].
And updating grid _ original _ num [ x _ original ] [ y _ original ], namely updating the number of data elements accompanying the grid so as to provide index information in the subsequent scanning process.
When the data in the target grid background is updated, the data in the first reference grid background and the data in the second reference grid background are updated simultaneously, specifically, the first dimension index of the first reference grid background is x _ left ═ x +25000)/50000+1600, y _ left ═ lon +25000)/50000+3600, after the calculation is completed, grid _ left [ x _ left ] [ y _ left ] and grid _ left _ num [ x _ left ] [ y _ left ] are updated simultaneously, the first dimension index of the second reference grid background is x _ right ═ lat-25000)/50000+1600, y _ right ═ lon-25000)/50000+3600, after the calculation is completed, grid _ right [ x _ right ] and right _ down [ x _ right ] are updated simultaneously.
After the grid background is updated, the position grids are scanned one by one, specifically, all the elements from the first column to the 7200 th column in the first row are firstly traversed in a row-first manner until all 3200 rows are traversed, for a specific position grid, three position grids with the same index in three sets of grid backgrounds can be read at a time, for example, when the position grid in the first row and the first column is calculated, after the calculation is completed, before the position grid in the first row and the second column is read, the position grid in the upper left sliding and the position grid in the lower right sliding are respectively calculated, and so on.
The specific calculation process is to calculate the distance between all the ships in the three types of grid backgrounds, the distance is a simplified distance, and can be actually represented by the absolute value of longitude difference and the absolute value of latitude difference of two ships, and when the distance is less than 0.008 degrees (about 889 meters near the equator), the ship is considered as a potential ship-to-ship event. And after the traversal of all the position grids is completed, the module outputs all the potential ship-berthing events.
In some embodiments, before acquiring the ship trajectory data, the method further comprises: and based on the historical track data, differentially allocating memory for the target grid background, the first reference grid background and the second reference grid background.
It can be understood that historical track data of all ships since 2011 can be acquired from HBase, a map is established between each track point and a grid background, the number of ships passing through or staying in the history of each position grid is counted after the track points of the ships are subjected to MMSI duplication removal, the number represents the heat degree of the grid, and memories related to the grid backgrounds and the ships are allocated according to the heat degree, so that the differential allocation of the memories is realized.
After the grid background is constructed, dynamic application and release of a large amount of memory resources during program operation generally reduce performance, and program collapse may be caused by insufficient resources, pre-allocation of memory of the grid background is an effective method, after memory is pre-allocated to the grid background occupying a large amount of memory resources, ship information of a position grid in the grid background can be quickly updated through ship position information, because a global grid system is constructed in advance, the maximum number of ships possibly contained in the position grid is assumed, namely enough memory resources are allocated to each position grid to accommodate the maximum number of ships, however, in actual conditions, no ship-by-ship event occurs on land, and ship-by-ship events rarely occur in large oceans because ship-by-ships generally occur in offshore or coastal water areas, in order to avoid memory waste, the heat degree of the position grid can be generated by using a large amount of ship history tracks, the real ship track enables the position grid to have credible heat, and the differentiated distribution of grid background memory can be realized according to the differentiated heat value, so that the aim of saving memory cost is fulfilled.
In the scheme, the calculated amount of the distance between the ships is limited by grid background mapping, and potential ship-approaching events are identified in a position grid through simple longitude and latitude comparison.
A plurality of sets of grid backgrounds with the same size are established by using a sliding window idea, and the boundary distribution of the ship in the position grid is converted into the internal distribution through grid background migration, so that potential ship-berthing events cannot be omitted in the grid scanning process. The high performance calculations result from one partial scan of all grids to identify all potential boat berthing events, with performance comparable to a multiple of the number of grids compared to full calculations without grid framing.
The idea of constructing multiple sets of grid backgrounds to realize sliding windows consumes a large amount of memory resources in the engineering realization process. Considering that the ship-berthing event occurs in the water area, the massive historical track of the ships provides clues for the areas where the ship-berthing event possibly occurs, and meanwhile, the historical track of the ships has the advantage of reflecting the heat of ship distribution in the water area, a large number of ships are gathered in some hot spot areas, and a small number of ships are distributed in other areas. Based on the knowledge, the distribution heat of all ships can be generated in the grid background by utilizing the historical tracks of the large number of ships, and the memory on the grid background is differentially distributed according to the differential heat.
The mesh background is differentially distributed with two purposes, firstly, the memory resource is saved, secondly, the memory model of the program is simplified through the memory pre-distribution, and the robustness of the program is improved. After the grid background is built, mapping the longitude and latitude positions of the global ships to the position grids in a timing mode, then scanning the grids one by one, rapidly calculating the distance between the ships in the position grids, and extracting potential ship-berthing events from a plurality of sets of grid backgrounds. And after the potential ship-berthing event is extracted, accurately calculating the potential event, finally generating the ship-berthing event meeting the service requirement, and storing the ship-berthing event into a MySQL and GeoMesa database for a user to use.
The ship-to-ship event recognition system provided by the invention is described below, and the ship-to-ship event recognition system described below and the ship-to-ship event recognition method described above can be referred to correspondingly.
As shown in fig. 3, the present invention also provides a ship-docking event recognition system, including: a first determination module 310, a second determination module 320, an acquisition module 330, a mapping module 340, and an output module 350.
The first determining module 310 is configured to determine a target grid background, where the target grid background is formed by a plurality of position grids with a side length equal to a first target length, which are constructed on a target map.
A second determining module 320, configured to translate the target grid background by a second target length along the diagonal of the position grid to a first direction and a second direction, respectively, and determine a first reference grid background and a second reference grid background, where the second direction is opposite to the first direction.
The obtaining module 330 is configured to obtain ship track data, where the ship track data includes position information of each track point.
The mapping module 340 is configured to map the ship trajectory data to a target background grid, a first reference grid background, and a second reference grid background, respectively, based on the position information corresponding to the ship trajectory data.
And the output module 350 is configured to determine a distance between every two trace points in each position grid of the target background grid, the first reference grid background and the second reference grid background, confirm that the distance between the two trace points is smaller than a target distance threshold value, and output a ship-approaching event record.
Fig. 4 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 4: a processor (processor)410, a communication Interface 420, a memory (memory)430 and a communication bus 440, wherein the processor 410, the communication Interface 420 and the memory 430 are communicated with each other via the communication bus 440. The processor 410 may invoke logic instructions in the memory 430 to perform a method of berthing event identification, the method comprising: determining a target grid background, wherein the target grid background is formed by a plurality of position grids with side length being a first target length constructed on a target map; translating the target grid background by a second target length along the diagonal of the position grid to a first direction and a second direction respectively, and determining a first reference grid background and a second reference grid background, wherein the second direction is opposite to the first direction; acquiring ship track data, wherein the ship track data comprises position information of each track point; respectively mapping ship track data to a target background grid, a first reference grid background and a second reference grid background based on position information corresponding to the ship track data; and determining the distance between every two track points in each position grid of the target background grid, the first reference grid background and the second reference grid background, confirming that the distance between the two track points is smaller than a target distance threshold value, and outputting a ship approach event record.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, which when executed by a computer, enable the computer to perform the method for identifying a berthing event provided by the above methods, the method comprising: determining a target grid background, wherein the target grid background is formed by a plurality of position grids with side length being a first target length constructed on a target map; translating the target grid background by a second target length along the diagonal of the position grid to a first direction and a second direction respectively, and determining a first reference grid background and a second reference grid background, wherein the second direction is opposite to the first direction; acquiring ship track data, wherein the ship track data comprises position information of each track point; respectively mapping ship track data to a target background grid, a first reference grid background and a second reference grid background based on position information corresponding to the ship track data; and determining the distance between every two track points in each position grid of the target background grid, the first reference grid background and the second reference grid background, confirming that the distance between the two track points is smaller than a target distance threshold value, and outputting a ship approach event record.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, is implemented to perform the provided method for detecting a ship-in event, the method comprising: determining a target grid background, wherein the target grid background is formed by a plurality of position grids with side length being a first target length constructed on a target map; translating the target grid background by a second target length along the diagonal of the position grid to a first direction and a second direction respectively, and determining a first reference grid background and a second reference grid background, wherein the second direction is opposite to the first direction; acquiring ship track data, wherein the ship track data comprises position information of each track point; respectively mapping ship track data to a target background grid, a first reference grid background and a second reference grid background based on position information corresponding to the ship track data; and determining the distance between every two track points in each position grid of the target background grid, the first reference grid background and the second reference grid background, confirming that the distance between the two track points is smaller than a target distance threshold value, and outputting a ship approach event record.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A ship berthing event identification method is characterized by comprising the following steps:
determining a target grid background, wherein the target grid background is formed by a plurality of position grids with side length being a first target length constructed on a target map;
translating the target grid background along the diagonal of the position grid by a second target length in a first direction and a second direction respectively, and determining a first reference grid background and a second reference grid background, wherein the second direction is opposite to the first direction;
acquiring ship track data, wherein the ship track data comprises position information of each track point;
respectively mapping the ship track data to the target background grid, the first reference grid background and the second reference grid background based on the position information corresponding to the ship track data;
and determining the distance between every two track points in each position grid of the target background grid, the first reference grid background and the second reference grid background, confirming that the distance between the two track points is smaller than a target distance threshold value, and outputting a ship-approaching event record.
2. The method of claim 1, further comprising:
determining the position of a center point of the ship based on the ship track data;
determining the distance between the central points of the two ships based on the distance between the two track points and the position of the central point of the ship;
and updating the ship-approaching event record based on the distance between the central points of the two ships and the target distance threshold value to obtain an updated ship-approaching event record.
3. The method of claim 1, further comprising:
determining bow direction information of the ship based on the ship track data;
and updating the ship-approaching event record based on the ship bow direction information of the ship to obtain an updated ship-approaching event record.
4. The method for identifying a ship approach event according to claim 1, wherein the acquiring ship trajectory data comprises:
obtaining the ship track data at intervals of a target time period threshold value;
and if the ship track data is not acquired, taking historical track data as the ship track data.
5. The method according to any one of claims 1 to 4, wherein the ship trajectory data comprises: the MMSI of the vessel, the longitude of the vessel, and the latitude of the vessel;
the mapping the ship track data to the target background grid, the first reference grid background and the second reference grid background respectively based on the position information corresponding to the ship track data includes:
establishing index information of the ship track data and the target background grid, the first reference grid background and the second reference grid background based on the longitude of the ship and the latitude of the ship;
adding the MMSI of the vessel, the longitude of the vessel, and the latitude of the vessel to the index information.
6. The ship-to-ship event identification method of claim 5, wherein the indexing the ship trajectory data with the target background grid, the first reference grid background and the second reference grid background based on the longitude of the ship and the latitude of the ship comprises:
establishing a first dimension index based on the longitude of the ship;
establishing a second-dimension index based on the latitude of the ship;
determining the index information based on the first dimension index and the second dimension index.
7. The method for identifying a ship approach event according to any one of claims 1 to 4, further comprising, before acquiring the ship trajectory data:
based on historical trajectory data, differentially allocating memory for the target grid background, the first reference grid background and the second reference grid background.
8. A system for identifying a berthing event, comprising:
the system comprises a first determination module, a second determination module and a third determination module, wherein the first determination module is used for determining a target grid background, and the target grid background is formed by a plurality of position grids with the side length being a first target length and constructed on a target map;
a second determining module, configured to translate the target grid background by a second target length along a diagonal of the position grid to a first direction and a second direction, respectively, and determine a first reference grid background and a second reference grid background, where the second direction is opposite to the first direction;
the acquisition module is used for acquiring ship track data, and the ship track data comprises position information of each track point;
the mapping module is used for mapping the ship track data to the target background grid, the first reference grid background and the second reference grid background respectively based on the position information corresponding to the ship track data;
and the output module is used for determining the distance between every two track points in each position grid of the target background grid, the first reference grid background and the second reference grid background, confirming that the distance between the two track points is smaller than a target distance threshold value, and outputting a ship-approaching event record.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method of identification of a berthing event according to any of claims 1 to 7.
10. A non-transitory computer readable storage medium, having stored thereon a computer program, wherein the computer program, when being executed by a processor, is adapted to carry out the steps of the method for identifying a berthing event according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110442571.0A CN113220678B (en) | 2021-04-23 | 2021-04-23 | Ship leaning event identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110442571.0A CN113220678B (en) | 2021-04-23 | 2021-04-23 | Ship leaning event identification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113220678A true CN113220678A (en) | 2021-08-06 |
| CN113220678B CN113220678B (en) | 2023-09-08 |
Family
ID=77089073
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110442571.0A Active CN113220678B (en) | 2021-04-23 | 2021-04-23 | Ship leaning event identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113220678B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113779031A (en) * | 2021-09-13 | 2021-12-10 | 上海船舶运输科学研究所 | Ship-to-ship refueling identification processing method and system |
| CN113779046A (en) * | 2021-11-15 | 2021-12-10 | 亿海蓝（北京）数据技术股份公司 | Irregular area index generation method, device, medium and electronic equipment |
| CN116863756A (en) * | 2023-09-05 | 2023-10-10 | 太极计算机股份有限公司 | Real-time early warning method, device and storage medium for offshore connection |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102968625A (en) * | 2012-12-14 | 2013-03-13 | 南京思创信息技术有限公司 | Ship distinguishing and tracking method based on trail |
| CN103303433A (en) * | 2013-05-21 | 2013-09-18 | 中国船舶工业集团公司第七〇八研究所 | Virtual test system and test method for ship performance |
| CN103631148A (en) * | 2013-08-28 | 2014-03-12 | 中国人民解放军海军大连舰艇学院 | AIS-based ship driving real-time virtual augmentation simulation system and method |
| CN110399676A (en) * | 2019-07-24 | 2019-11-01 | 李燕 | Northwest Pacific three-dimensional oil spilling business contingency forecast and assessment system |
| CN110703759A (en) * | 2019-10-29 | 2020-01-17 | 青岛科技大学 | Ship collision prevention processing method for multi-ship game |
| CN111179638A (en) * | 2020-01-08 | 2020-05-19 | 中国船舶重工集团公司第七二四研究所 | Ship AIS target navigation monitoring method based on time sequence |
| US20200250992A1 (en) * | 2019-01-31 | 2020-08-06 | Brunswick Corporation | Marine Propulsion Control System and Method |
| CN111581314A (en) * | 2020-04-26 | 2020-08-25 | 亿海蓝（北京）数据技术股份公司 | Berth identification method and device based on ship track |
| CN112132346A (en) * | 2020-09-24 | 2020-12-25 | 中国科学院空天信息创新研究院 | Ship navigation track prediction method based on ship type |
-
2021
- 2021-04-23 CN CN202110442571.0A patent/CN113220678B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102968625A (en) * | 2012-12-14 | 2013-03-13 | 南京思创信息技术有限公司 | Ship distinguishing and tracking method based on trail |
| CN103303433A (en) * | 2013-05-21 | 2013-09-18 | 中国船舶工业集团公司第七〇八研究所 | Virtual test system and test method for ship performance |
| CN103631148A (en) * | 2013-08-28 | 2014-03-12 | 中国人民解放军海军大连舰艇学院 | AIS-based ship driving real-time virtual augmentation simulation system and method |
| US20200250992A1 (en) * | 2019-01-31 | 2020-08-06 | Brunswick Corporation | Marine Propulsion Control System and Method |
| CN110399676A (en) * | 2019-07-24 | 2019-11-01 | 李燕 | Northwest Pacific three-dimensional oil spilling business contingency forecast and assessment system |
| CN110703759A (en) * | 2019-10-29 | 2020-01-17 | 青岛科技大学 | Ship collision prevention processing method for multi-ship game |
| CN111179638A (en) * | 2020-01-08 | 2020-05-19 | 中国船舶重工集团公司第七二四研究所 | Ship AIS target navigation monitoring method based on time sequence |
| CN111581314A (en) * | 2020-04-26 | 2020-08-25 | 亿海蓝（北京）数据技术股份公司 | Berth identification method and device based on ship track |
| CN112132346A (en) * | 2020-09-24 | 2020-12-25 | 中国科学院空天信息创新研究院 | Ship navigation track prediction method based on ship type |
Non-Patent Citations (3)
| Title |
|---|
| HUANHUAN LI等: "a dimensionality reduction-based multi-step clustering method for robust vessel trajectory analysis", SENSORS, vol. 8, no. 17, pages 1792 * |
| 宁建强;黄涛;刁博宇;赵瑞莲;毕经平;: "一种基于海量船舶轨迹数据的细粒度网格海上交通密度计算方法", 计算机工程与科学, vol. 37, no. 12, pages 2242 - 2249 * |
| 郭延华等: "一种基于极端尺度变化的船舶识别方法研究", 计算机应用与软件, vol. 38, no. 1, pages 171 - 178 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113779031A (en) * | 2021-09-13 | 2021-12-10 | 上海船舶运输科学研究所 | Ship-to-ship refueling identification processing method and system |
| CN113779031B (en) * | 2021-09-13 | 2022-04-29 | 上海船舶运输科学研究所有限公司 | Ship-to-ship refueling identification processing method and system |
| WO2023035309A1 (en) * | 2021-09-13 | 2023-03-16 | 上海船舶运输科学研究所有限公司 | Ship-to-ship refueling identification processing method and system |
| CN113779046A (en) * | 2021-11-15 | 2021-12-10 | 亿海蓝（北京）数据技术股份公司 | Irregular area index generation method, device, medium and electronic equipment |
| CN116863756A (en) * | 2023-09-05 | 2023-10-10 | 太极计算机股份有限公司 | Real-time early warning method, device and storage medium for offshore connection |
| CN116863756B (en) * | 2023-09-05 | 2023-12-15 | 太极计算机股份有限公司 | Real-time early warning method, device and storage medium for offshore connection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113220678B (en) | 2023-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113220678A (en) | Ship berthing event identification method and system | |
| CN113450596B (en) | Space-time DP method based on ship track feature point extraction | |
| CN111291776B (en) | Channel information extraction method based on crowd source track data | |
| CN112883820B (en) | Road target 3D detection method and system based on laser radar point cloud | |
| CN113190515B (en) | Heterogeneous parallel computing-based urban mass point cloud coordinate transformation method | |
| CN114419085A (en) | Automatic building contour line extraction method and device, terminal device and storage medium | |
| CN112782743B (en) | Vehicle positioning method and device, computer equipment and storage medium | |
| CN113723715B (en) | Method, system, equipment and storage medium for automatically matching public transport network with road network | |
| CN112577470B (en) | Method and system for monitoring dynamic subsidence basin of mining area by fusion of UAV and InSAR | |
| CN111914045B (en) | Data compression method, device, terminal equipment and storage medium | |
| CN114660561A (en) | AIS and radar track association method and device | |
| CN111813877A (en) | Flight path extraction method and device | |
| CN113420004A (en) | Tunnel point cloud data storage method and device, computer equipment and storage medium | |
| CN111141768B (en) | Method and device for acquiring rock wettability change in crude oil displacement | |
| CN112100308A (en) | Similarity query method for Beidou space-time trajectory | |
| CN112632399A (en) | Topological relation obtaining method and device based on spatial position and storage medium | |
| CN110174115B (en) | Method and device for automatically generating high-precision positioning map based on perception data | |
| CN115937466B (en) | GIS-fused three-dimensional model generation method, system and storage medium | |
| CN116958089A (en) | Petroleum pipeline crack detection method based on dual-attention mechanism | |
| CN111369604A (en) | Grid-based topographic feature point extraction method and processing terminal | |
| CN110889979B (en) | Inland waterway data fusion method and device | |
| CN112614226A (en) | Point cloud multi-view feature fusion method and device | |
| CN116643300B (en) | Satellite navigation data distributed real-time processing method and system based on map mapping | |
| CN115438247B (en) | Method, device and equipment for discriminating multiple vessels based on track | |
| CN117315001B (en) | Method and system for rapidly detecting building area based on laser scanning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |